Skip to content

[KQP] Fix plan olap filter selectivity estimation #9936

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 3 commits into from
Oct 1, 2024
Merged

[KQP] Fix plan olap filter selectivity estimation #9936

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
7d55999
[KQP] Fix Olap filter selectivity estimation
pashandor789 Oct 1, 2024
cfe39f5
[KQP] Fix Olap filter selectivity estimation
pashandor789 Oct 1, 2024
aacc428
.
pashandor789 Oct 1, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 5 additions & 4 deletions ydb/core/kqp/opt/kqp_query_plan.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1721,12 +1721,13 @@ class TxPlanSerializer {

AddReadTableSettings(op, read, readInfo);

if (read.Maybe<TKqpReadOlapTableRangesBase>()) {
if (auto maybeRead = read.Maybe<TKqpReadOlapTableRangesBase>()) {
op.Properties["SsaProgram"] = GetSsaProgramInJsonByTable(table, planNode.StageProto);
AddOptimizerEstimates(op, maybeRead.Cast().Process());
} else {
AddOptimizerEstimates(op, read);
}

AddOptimizerEstimates(op, read);

auto readName = GetNameByReadType(readInfo.Type);
op.Properties["Name"] = readName;
ui32 operatorId = AddOperator(planNode, readName, std::move(op));
Expand Down Expand Up @@ -2386,7 +2387,7 @@ void RemoveStats(NJson::TJsonValue& plan) {

NJson::TJsonValue SimplifyQueryPlan(NJson::TJsonValue& plan) {
static const THashSet<TString> redundantNodes = {
"UnionAll",
"UnionAll",
"Broadcast",
"Map",
"HashShuffle",
Expand Down
0 ...p/ut/join/data/queries/test_join_hint.sql → .../ut/join/data/queries/test_join_hint1.sql
View file
Open in desktop
File renamed without changes.
72 changes: 41 additions & 31 deletions ydb/core/kqp/ut/join/kqp_join_order_ut.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,6 +5,7 @@

#include <util/string/printf.h>

#include <algorithm>
#include <fstream>
#include <regex>

Expand Down Expand Up @@ -93,8 +94,17 @@ static TKikimrRunner GetKikimrWithJoinSettings(bool useStreamLookupJoin = false,

void PrintPlan(const TString& plan) {
Cout << plan << Endl;
NYdb::NConsoleClient::TQueryPlanPrinter queryPlanPrinter(NYdb::NConsoleClient::EDataFormat::PrettyTable, true, Cout, 150);
NYdb::NConsoleClient::TQueryPlanPrinter queryPlanPrinter(NYdb::NConsoleClient::EDataFormat::PrettyTable, true, Cout, 0);
queryPlanPrinter.Print(plan);

std::string joinOrder = GetJoinOrder(plan).GetStringRobust();

Cout << "JoinOrder: " << joinOrder << Endl;
std::replace(joinOrder.begin(), joinOrder.end(), '[', '(');
std::replace(joinOrder.begin(), joinOrder.end(), ']', ')');
std::replace(joinOrder.begin(), joinOrder.end(), ',', ' ');
joinOrder.erase(std::remove(joinOrder.begin(), joinOrder.end(), '\"'), joinOrder.end());
Cout << "JoinOrder" << joinOrder << Endl;
}

class TChainTester {
Expand Down Expand Up @@ -355,13 +365,6 @@ Y_UNIT_TEST_SUITE(KqpJoinOrder) {
}
}

/* tpcds23 has > 1 result sets */
Y_UNIT_TEST_XOR_OR_BOTH_FALSE(TPCDS23, StreamLookupJoin, ColumnStore) {
ExplainJoinOrderTestDataQueryWithStats(
"queries/tpcds23.sql", "stats/tpcds1000s.json", StreamLookupJoin, ColumnStore
);
}

Y_UNIT_TEST_XOR_OR_BOTH_FALSE(FiveWayJoin, StreamLookupJoin, ColumnStore) {
ExecuteJoinOrderTestDataQueryWithStats(
"queries/five_way_join.sql", "stats/basic.json", StreamLookupJoin, ColumnStore
Expand Down Expand Up @@ -410,14 +413,6 @@ Y_UNIT_TEST_SUITE(KqpJoinOrder) {
);
}

Y_UNIT_TEST_XOR_OR_BOTH_FALSE(TestJoinHint, StreamLookupJoin, ColumnStore) {
CheckJoinCardinality("queries/test_join_hint.sql", "stats/basic.json", "InnerJoin (Grace)", 10e6, StreamLookupJoin, ColumnStore);
}

Y_UNIT_TEST_XOR_OR_BOTH_FALSE(TestJoinHint2, StreamLookupJoin, ColumnStore) {
CheckJoinCardinality("queries/test_join_hint2.sql", "stats/basic.json", "InnerJoin (MapJoin)", 1, StreamLookupJoin, ColumnStore);
}

Y_UNIT_TEST_XOR_OR_BOTH_FALSE(FiveWayJoinWithConstantFold, StreamLookupJoin, ColumnStore) {
ExecuteJoinOrderTestDataQueryWithStats("queries/five_way_join_with_constant_fold.sql", "stats/basic.json", StreamLookupJoin, ColumnStore);
}
Expand Down Expand Up @@ -458,6 +453,13 @@ Y_UNIT_TEST_SUITE(KqpJoinOrder) {
ExecuteJoinOrderTestDataQueryWithStats("queries/tpcds16.sql", "stats/tpcds1000s.json", StreamLookupJoin, ColumnStore);
}

/* tpcds23 has > 1 result sets */
Y_UNIT_TEST_XOR_OR_BOTH_FALSE(TPCDS23, StreamLookupJoin, ColumnStore) {
ExplainJoinOrderTestDataQueryWithStats(
"queries/tpcds23.sql", "stats/tpcds1000s.json", StreamLookupJoin, ColumnStore
);
}

Y_UNIT_TEST_XOR_OR_BOTH_FALSE(TPCDS34, StreamLookupJoin, ColumnStore) {
ExecuteJoinOrderTestDataQueryWithStats("queries/tpcds34.sql", "stats/tpcds1000s.json", StreamLookupJoin, ColumnStore);
}
Expand Down Expand Up @@ -494,6 +496,14 @@ Y_UNIT_TEST_SUITE(KqpJoinOrder) {
ExecuteJoinOrderTestDataQueryWithStats("queries/tpcds96.sql", "stats/tpcds1000s.json", StreamLookupJoin, ColumnStore);
}

Y_UNIT_TEST_XOR_OR_BOTH_FALSE(TestJoinHint1, StreamLookupJoin, ColumnStore) {
CheckJoinCardinality("queries/test_join_hint1.sql", "stats/basic.json", "InnerJoin (Grace)", 10e6, StreamLookupJoin, ColumnStore);
}

Y_UNIT_TEST_XOR_OR_BOTH_FALSE(TestJoinHint2, StreamLookupJoin, ColumnStore) {
CheckJoinCardinality("queries/test_join_hint2.sql", "stats/basic.json", "InnerJoin (MapJoin)", 1, StreamLookupJoin, ColumnStore);
}

Y_UNIT_TEST_XOR_OR_BOTH_FALSE(TestJoinOrderHintsSimple, StreamLookupJoin, ColumnStore) {
auto plan = ExecuteJoinOrderTestDataQueryWithStats("queries/join_order_hints_simple.sql", "stats/basic.json", StreamLookupJoin, ColumnStore);
UNIT_ASSERT_VALUES_EQUAL(GetJoinOrder(plan).GetStringRobust(), R"(["T",["R","S"]])") ;
Expand All @@ -512,7 +522,7 @@ Y_UNIT_TEST_SUITE(KqpJoinOrder) {
UNIT_ASSERT_C(joinOrder.find(R"(["T","U"])") != TString::npos, joinOrder);
}

void JoinOrderTestWithOverridenStats(const TString& queryPath, const TString& statsPath, TString correctJoinOrderPath, bool useStreamLookupJoin, bool useColumnStore
void CanonizedJoinOrderTest(const TString& queryPath, const TString& statsPath, TString correctJoinOrderPath, bool useStreamLookupJoin, bool useColumnStore
) {
auto kikimr = GetKikimrWithJoinSettings(useStreamLookupJoin, GetStatic(statsPath));
auto db = kikimr.GetTableClient();
Expand Down Expand Up @@ -557,44 +567,44 @@ Y_UNIT_TEST_SUITE(KqpJoinOrder) {
}
}

Y_UNIT_TEST_XOR_OR_BOTH_FALSE(OverrideStatsTPCH2, StreamLookupJoin, ColumnStore) {
JoinOrderTestWithOverridenStats(
Y_UNIT_TEST_XOR_OR_BOTH_FALSE(CanonizedJoinOrderTPCH2, StreamLookupJoin, ColumnStore) {
CanonizedJoinOrderTest(
"queries/tpch2.sql", "stats/tpch1000s.json", "join_order/tpch2_1000s.json", StreamLookupJoin, ColumnStore
);
}

Y_UNIT_TEST_XOR_OR_BOTH_FALSE(OverrideStatsTPCH9, StreamLookupJoin, ColumnStore) {
JoinOrderTestWithOverridenStats(
Y_UNIT_TEST_XOR_OR_BOTH_FALSE(CanonizedJoinOrderTPCH9, StreamLookupJoin, ColumnStore) {
CanonizedJoinOrderTest(
"queries/tpch9.sql", "stats/tpch1000s.json", "join_order/tpch9_1000s.json", StreamLookupJoin, ColumnStore
);
}

Y_UNIT_TEST_XOR_OR_BOTH_FALSE(OverrideStatsTPCDS64, StreamLookupJoin, ColumnStore) {
JoinOrderTestWithOverridenStats(
Y_UNIT_TEST_XOR_OR_BOTH_FALSE(CanonizedJoinOrderTPCDS64, StreamLookupJoin, ColumnStore) {
CanonizedJoinOrderTest(
"queries/tpcds64.sql", "stats/tpcds1000s.json", "join_order/tpcds64_1000s.json", StreamLookupJoin, ColumnStore
);
}

Y_UNIT_TEST_XOR_OR_BOTH_FALSE(OverrideStatsTPCDS64_small, StreamLookupJoin, ColumnStore) {
JoinOrderTestWithOverridenStats(
Y_UNIT_TEST_XOR_OR_BOTH_FALSE(CanonizedJoinOrderTPCDS64_small, StreamLookupJoin, ColumnStore) {
CanonizedJoinOrderTest(
"queries/tpcds64_small.sql", "stats/tpcds1000s.json", "join_order/tpcds64_small_1000s.json", StreamLookupJoin, ColumnStore
);
}

Y_UNIT_TEST_XOR_OR_BOTH_FALSE(OverrideStatsTPCDS78, StreamLookupJoin, ColumnStore) {
JoinOrderTestWithOverridenStats(
Y_UNIT_TEST_XOR_OR_BOTH_FALSE(CanonizedJoinOrderTPCDS78, StreamLookupJoin, ColumnStore) {
CanonizedJoinOrderTest(
"queries/tpcds78.sql", "stats/tpcds1000s.json", "join_order/tpcds78_1000s.json", StreamLookupJoin, ColumnStore
);
}

Y_UNIT_TEST(TPCC) {
JoinOrderTestWithOverridenStats(
Y_UNIT_TEST(CanonizedJoinOrderTPCC) {
CanonizedJoinOrderTest(
"queries/tpcc.sql", "stats/tpcc.json", "join_order/tpcc.json", false, false
);
}

Y_UNIT_TEST(LookupBug) {
JoinOrderTestWithOverridenStats(
Y_UNIT_TEST(CanonizedJoinOrderLookupBug) {
CanonizedJoinOrderTest(
"queries/lookupbug.sql", "stats/lookupbug.json", "join_order/lookupbug.json", false, false
);
}
Expand Down